Back to skill

Security audit

AnyAPI

Security checks for vulnerabilities and agentic risk

Overview

The AnyAPI workflow is coherent, but its automatic setup runs unverified downloaded code and under-discloses broader changes to installed agent skills.

Review and approve the CLI installation separately before allowing automatic setup, including any skills it adds to other agents. Prefer a reviewed, version-specific installation with integrity verification. Send only necessary information through OOMOL and AnyAPI, account for paid requests, and retain the existing confirmation requirements for writes. The remote installer and downloaded CLI were not verified.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The supplied command executes an installer hosted on cli.oomol.com, with no visible connection to AnyAPI or its declared data operations. Nothing supplied establishes this installation as a supporting implementation detail for AnyAPI. The downloaded script is not included, so its further behavior cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The fallback pipes a mutable remote script directly into Bash without verifying its contents or integrity; the PowerShell alternative uses the equivalent download-and-execute pattern. Compromise of the distribution endpoint could execute attacker-controlled code with the agent's local privileges, exposing accessible files and credentials. Restricting installation to a missing-CLI error reduces exposure frequency but does not make execution safe.

Content

Scanner excerpt · SKILL.md (reported line 135)May include surrounding context.

The execution workflow lacks a privacy warning about transmitting user-provided payloads to third-party services.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The workflow instructs the agent to submit a JSON payload through the OOMOL connector to AnyAPI, but does not warn that user-provided inputs are disclosed to those services. The credential-handling explanation does not address payload privacy, particularly when inputs contain personal information such as email addresses.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 156)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources